Papers › The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery

12 Aug 2024arXiv:2408.06292archive 2025-07-28

Chris Lu, Cong Lu, Robert Tjarko Lange, Jakob Foerster, Jeff Clune, David Ha

One of the grand challenges of artificial general intelligence is developing agents capable of conducting scientific research and discovering new knowledge. While frontier models have already been used as aides to human scientists, e.g. for brainstorming ideas, writing code, or prediction tasks, they still conduct only a small part of the scientific process. This paper presents the first comprehensive framework for fully automatic scientific discovery, enabling frontier large language models to perform research independently and communicate their findings. We introduce The AI Scientist, which generates novel research ideas, writes code, executes experiments, visualizes results, describes its findings by writing a full scientific paper, and then runs a simulated review process for evaluation. In principle, this process can be repeated to iteratively develop ideas in an open-ended fashion, acting like the human scientific community. We demonstrate its versatility by applying it to three distinct subfields of machine learning: diffusion modeling, transformer-based language modeling, and learning dynamics. Each idea is implemented and developed into a full paper at a cost of less than $15 per paper. To evaluate the generated papers, we design and validate an automated reviewer, which we show achieves near-human performance in evaluating paper scores. The AI Scientist can produce papers that exceed the acceptance threshold at a top machine learning conference as judged by our automated reviewer. This approach signifies the beginning of a new era in scientific discovery in machine learning: bringing the transformative benefits of AI agents to the entire research process of AI itself, and taking us closer to a world where endless affordable creativity and innovation can be unleashed on the world's most challenging problems. Our code is open-sourced at https://github.com/SakanaAI/AI-Scientist

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 11 code samples harvested from 2 repositories linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 9 ran (6 with no instrument failure; 3 where Syntology's instrument failed); community (archive-listed): 2 samples from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

sakanaai/ai-scientist officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 9 samples, 9 ran (3 instrument-failed) · 0 unverified report
Masao-Taketani/AI-Scientist-with-Local-LLMs pytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

11 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
3ran · our draft was wrong
6ran
1unverified

Licence: 9 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

sakanaai/ai-scientist official repository 9 samples, 9 ran (3 instrument-failed) · 0 unverified
extract_json_between_markers in 5 papers ai_scientist/llm.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 41adbcc04070fd12 · report fixture: signature llm_output:str/0/str · returned dict · level recorded 2026-09-24
generate_color_palette example_papers/layerwise_lr_grokking/plot.py ran · our draft was wrong licence not identified · pointer only · de494a578ed3156e · report fixture: signature n:int/0/int · returned list · level recorded 2026-09-24
get_data in 223 papers example_papers/layerwise_lr_grokking/experiment.py ran licence not identified · pointer only · ef71cac55b75b747 · report fixture: signature operation:str/0/str, prime:int/0/int, training_fraction:float/0/float, batch_size:int/0/int · returned tuple · level recorded 2026-09-24
load_review ai_scientist/perform_review.py ran · our draft was wrong licence not identified · pointer only · 0560771a47a3e327 · report fixture: signature path:str/0/str · returned str · level recorded 2026-09-24
operation_mod_p_data example_papers/layerwise_lr_grokking/experiment.py ran licence not identified · pointer only · ef0e4401922abbd5 · report fixture: signature operation:str/0/str, p:int/0/int, frac_train:float/0/float · returned ModSumDataset · level recorded 2026-09-24
perform_experiments ai_scientist/perform_experiments.py ran licence not identified · pointer only · 5dfa236b6bc7969c · report fixture: signature idea:dict/0/?, folder_name:str/0/str, coder:MockCoder/0/?, baseline_results:dict/0/? · returned bool · level recorded 2026-09-24
run_experiment in 22 papers ai_scientist/perform_experiments.py ran licence not identified · pointer only · 8d71b435fe16e51f · report fixture: signature folder_name:str/0/str, run_num:int/0/int, timeout:int/0/int · returned tuple · level recorded 2026-09-24
run_plotting ai_scientist/perform_experiments.py ran licence not identified · pointer only · 4faf099f4b9d5c34 · report fixture: signature folder_name:str/0/str, timeout:int/0/int · returned tuple · level recorded 2026-09-24
train in 522 papers example_papers/layerwise_lr_grokking/experiment.py ran licence not identified · pointer only · a8a8eb2391a886e7 · report fixture: signature model:callable/0/?, train_loader:list/1/tuple, optimizer:SGD/0/?, scheduler:StepLR/0/?, device:str/0/str, num_train_batches:int/0/int · returned dict · level recorded 2026-09-24
Masao-Taketani/AI-Scientist-with-Local-LLMs community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
get_available_gpus launch_scientist.py ran · honoured contract Apache-2.0 (permissive) · b9a353fd9f420101 · report fixture: signature gpu_ids:str/0/str · returned list · level recorded 2026-09-22
train in 522 papers templates/nanoGPT/experiment.py unverified Apache-2.0 (permissive) · d3a0ec611e5c88d1 · report

Tasks

Language ModelingLanguage Modellingscientific discovery

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections